将彩色图像转换为灰度文件 HSV HSI 格式

彩色图像转换为灰度文件

.1 使用opencv

以代码：

import cv2 as cvimg = cv.imread('D:/xiazai/1.jpg',1)img_1 = cv.cvtColor(img,cv.COLOR_BGR2GRAY)cv.imshow('gray',img_1)cv.imshow('colour',img)cv.waitKey(0)

效果：

.2 不使用opencv

以代码：

from PIL import ImageI = Image.open('D:/xiazai/1.jpg')L = I.convert('L')L.show()

效果：

彩色图像转换为HSV、HSI文件

.1 HSV和HSI简介

HSV颜色空间中，H是Hue（色度）的缩写，S是Saturation（饱和度）的缩写，V是Value（亮度）的缩写。色度通常用来从宏观上区分某一种颜色，例如：白、黄、青、绿、品红、红、蓝、黑等就是色度；饱和度指的是颜色的纯度，通常情况下，颜色越鲜艳，饱和度越高，颜色越暗淡，饱和度越低；亮度指的是颜色的明暗程度，亮度越高，颜色越亮，亮度越低，颜色越暗。

HSV颜色空间不适合显示器系统，但是更符合人眼的视觉特性，因此通常会将颜色从RGB空间域转换到HSV颜色空间进行处理，然后在换回RGB域进行显示。

HSI颜色空间中，H和S与HSV颜色空间中的含义相同，I是Intensity（强度）的缩写。HSI颜色空间与HSV颜色空间很相近，但彼此之家并不相同。

.2 实现

转换为HSV：

代码：

# open-cv library is installed as cv2 in python# import cv2 library into this programimport cv2 as cv# read an image using imread() function of cv2# we have to pass only the path of the imageimg = cv.imread('D:/xiazai/1.jpg',1)# displaying the image using imshow() function of cv2# In this : 1st argument is name of the frame# 2nd argument is the image matrixcv.imshow('original image',img)# converting the colourfull image into HSV format image# using cv2.COLOR_BGR2HSV argument of# the cvtColor() function of cv2# in this :# ist argument is the image matrix# 2nd argument is the attributehsv = cv.cvtColor(img, cv.COLOR_BGR2HSV)# displaying the Hsv format imagecv.imshow('HSV format image',hsv)cv.waitKey(0)

效果：

转换为HSI：

代码：

import cv2import numpy as npdef rgbtohsi(rgb_lwpImg):rows = int(rgb_lwpImg.shape[0])cols = int(rgb_lwpImg.shape[1])b, g, r = cv2.split(rgb_lwpImg)# 归一化到[0,1]b = b / 255.0g = g / 255.0r = r / 255.0hsi_lwpImg = rgb_lwpImg.copy()H, S, I = cv2.split(hsi_lwpImg)for i in range(rows):for j in range(cols):num = 0.5 * ((r[i, j]-g[i, j])+(r[i, j]-b[i, j]))den = np.sqrt((r[i, j]-g[i, j])**2+(r[i, j]-b[i, j])*(g[i, j]-b[i, j]))theta = float(np.arccos(num/den))if den == 0:H = 0elif b[i, j] <= g[i, j]:H = thetaelse:H = 2*3.14169265 - thetamin_RGB = min(min(b[i, j], g[i, j]), r[i, j])sum = b[i, j]+g[i, j]+r[i, j]if sum == 0:S = 0else:S = 1 - 3*min_RGB/sumH = H/(2*3.14159265)I = sum/3.0# 输出HSI图像，扩充到255以方便显示，一般H分量在[0,2pi]之间，S和I在[0,1]之间hsi_lwpImg[i, j, 0] = H*255hsi_lwpImg[i, j, 1] = S*255hsi_lwpImg[i, j, 2] = I*255return hsi_lwpImgif __name__ == '__main__':rgb_lwpImg = cv2.imread("D:/xiazai/1.jpg")hsi_lwpImg = rgbtohsi(rgb_lwpImg)cv2.imshow('lena.jpg', rgb_lwpImg)cv2.imshow('hsi_lwpImg', hsi_lwpImg)key = cv2.waitKey(0) & 0xFFif key == ord('q'):cv2.destroyAllWindows()

效果：

车牌字符分割

首先将车牌转为灰度，之后提取边缘轮廓进行二值化处理，标出车牌位置进行切割和识别：

以代码：

import cv2import numpy as npimport osdef stackImages(scale, imgArray):"""将多张图像压入同一个窗口显示:param scale:float类型，输出图像显示百分比，控制缩放比例，0.5=图像分辨率缩小一半:param imgArray:元组嵌套列表，需要排列的图像矩阵:return:输出图像"""rows = len(imgArray)cols = len(imgArray[0])rowsAvailable = isinstance(imgArray[0], list)# 用空图片补齐for i in range(rows):tmp = cols - len(imgArray[i])for j in range(tmp):img = np.zeros((imgArray[0][0].shape[0], imgArray[0][0].shape[1]), dtype='uint8')imgArray[i].append(img)# 判断维数if rows>=2:width = imgArray[0][0].shape[1]height = imgArray[0][0].shape[0]else:width = imgArray[0].shape[1]height = imgArray[0].shape[0]if rowsAvailable:for x in range(0, rows):for y in range(0, cols):if imgArray[x][y].shape[:2] == imgArray[0][0].shape[:2]:imgArray[x][y] = cv2.resize(imgArray[x][y], (0, 0), None, scale, scale)else:imgArray[x][y] = cv2.resize(imgArray[x][y], (imgArray[0][0].shape[1], imgArray[0][0].shape[0]),None, scale, scale)if len(imgArray[x][y].shape) == 2:imgArray[x][y] = cv2.cvtColor(imgArray[x][y], cv2.COLOR_GRAY2BGR)imageBlank = np.zeros((height, width, 3), np.uint8)hor = [imageBlank] * rowshor_con = [imageBlank] * rowsfor x in range(0, rows):hor[x] = np.hstack(imgArray[x])ver = np.vstack(hor)else:for x in range(0, rows):if imgArray[x].shape[:2] == imgArray[0].shape[:2]:imgArray[x] = cv2.resize(imgArray[x], (0, 0), None, scale, scale)else:imgArray[x] = cv2.resize(imgArray[x], (imgArray[0].shape[1], imgArray[0].shape[0]), None, scale, scale)if len(imgArray[x].shape) == 2: imgArray[x] = cv2.cvtColor(imgArray[x], cv2.COLOR_GRAY2BGR)hor = np.hstack(imgArray)ver = horreturn ver# 分割结果输出路径output_dir = "./output"# 车牌路径file_path="./car/"# 读取所有车牌cars = os.listdir(file_path)cars.sort()# 循环操作每一张车牌for car in cars:# 读取图片print("正在处理"+file_path+car)src = cv2.imread(file_path+car)img = src.copy()# 预处理去除螺丝点cv2.circle(img, (145, 20), 10, (255, 0, 0), thickness=-1)cv2.circle(img, (430, 20), 10, (255, 0, 0), thickness=-1)cv2.circle(img, (145, 170), 10, (255, 0, 0), thickness=-1)cv2.circle(img, (430, 170), 10, (255, 0, 0), thickness=-1)cv2.circle(img, (180, 90), 10, (255, 0, 0), thickness=-1)# 转灰度gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 二值化adaptive_thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 333, 1)# 闭运算kernel = np.ones((5, 5), int)morphologyEx = cv2.morphologyEx(adaptive_thresh, cv2.MORPH_CLOSE, kernel)# 找边界contours, hierarchy = cv2.findContours(morphologyEx, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)# 画边界img_1 = img.copy()cv2.drawContours(img_1, contours, -1, (0, 0, 0), -1)imgStack = stackImages(0.7, ([src, img, gray], [adaptive_thresh, morphologyEx, img_1]))cv2.imshow("imgStack", imgStack)cv2.waitKey(0)# 转灰度为了方便切割gray_1 = cv2.cvtColor(img_1, cv2.COLOR_BGR2GRAY)# 每一列的白色数量white = []# 每一列的黑色数量black = []# 区域高度取决于图片高height = gray_1.shape[0]# 区域宽度取决于图片宽width = gray_1.shape[1]# 最大白色数量white_max = 0# 最大黑色数量black_max = 0# 计算每一列的黑白色像素总和for i in range(width):s = 0 # 这一列白色总数t = 0 # 这一列黑色总数for j in range(height):if gray_1[j][i] == 255:s += 1if gray_1[j][i] == 0:t += 1white_max = max(white_max, s)black_max = max(black_max, t)white.append(s)black.append(t)# 找到右边界def find_end(start):end = start + 1for m in range(start + 1, width - 1):# 基本全黑的列视为边界if black[m] >= black_max * 0.95: # 0.95这个参数请多调整，对应下面的0.05end = mbreakreturn end# 临时变量n = 1# 起始位置start = 1# 结束位置end = 2# 分割结果数量num=0# 分割结果res = []# 保存分割结果路径,以图片名命名output_path= output_dir + car.split('.')[0]if not os.path.exists(output_path):os.makedirs(output_path)# 从左边网右边遍历while n < width - 2:n += 1# 找到白色即为确定起始地址# 不可以直接 white[n] > white_maxif white[n] > 0.05 * white_max:start = n# 找到结束坐标end = find_end(start)# 下一个的起始地址n = end# 确保找到的是符合要求的,过小不是车牌号if end - start > 10:# 分割char = gray_1[1:height, start - 5:end + 5]# 保存分割结果到文件cv2.imwrite(output_path+'/' + str(num) + '.jpg',char)num+=1# 重新绘制大小char = cv2.resize(char, (300, 300), interpolation=cv2.INTER_CUBIC)# 添加到结果集合res.append(char)# cv2.imshow("imgStack", char)# cv2.waitKey(0)# 构造结果元祖方便结果展示res2 = (res[:2], res[2:4], res[4:6], res[6:])# 显示结果imgStack = stackImages(0.5, res2)cv2.imshow("imgStack", imgStack)cv2.waitKey(0)cv2.destroyAllWindows()

效果（部分）：